Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI
出版年份 2021 全文链接
标题
Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI
作者
关键词
Information fusion, Explainable AI, xAI, Graph Neural Networks, Multi-modal causability, Knowledge graphs, Counterfactuals
出版物
Information Fusion
Volume 71, Issue -, Pages 28-37
出版商
Elsevier BV
发表日期
2021-01-27
DOI
10.1016/j.inffus.2021.01.008
参考文献
相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。- The long road to fairer algorithms
- (2020) Matt J. Kusner et al. NATURE
- Bridging the “last mile” gap between AI implementation and operation: “data awareness” that matters
- (2020) Federico Cabitza et al. Annals of Translational Medicine
- Explainable decision forest: Transforming a decision forest into an interpretable tree
- (2020) Omer Sagi et al. Information Fusion
- Explainability in deep reinforcement learning
- (2020) Alexandre Heuillet et al. KNOWLEDGE-BASED SYSTEMS
- The seven tools of causal inference, with reflections on machine learning
- (2019) Judea Pearl COMMUNICATIONS OF THE ACM
- Biomedical image augmentation using Augmentor
- (2019) Marcus D Bloice et al. BIOINFORMATICS
- Why imaging data alone is not enough: AI-based integration of imaging, omics, and clinical data
- (2019) Andreas Holzinger et al. EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING
- Feasibility study of a multi-criteria decision-making based hierarchical model for multi-modality feature and multi-classifier fusion: Applications in medical prognosis prediction
- (2019) Qiang He et al. Information Fusion
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
- (2019) Alejandro Barredo Arrieta et al. Information Fusion
- Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data
- (2019) Felix Sattler et al. IEEE Transactions on Neural Networks and Learning Systems
- In silico cancer research towards 3R
- (2018) Claire Jean-Quartier et al. BMC CANCER
- A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
- (2018) HongYun Cai et al. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
- Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
- (2018) Tian Xie et al. PHYSICAL REVIEW LETTERS
- Clinically applicable deep learning for diagnosis and referral in retinal disease
- (2018) Jeffrey De Fauw et al. NATURE MEDICINE
- Interactive machine learning: experimental evidence for the human in the algorithmic loop
- (2018) Andreas Holzinger et al. APPLIED INTELLIGENCE
- Dermatologist-level classification of skin cancer with deep neural networks
- (2017) Andre Esteva et al. NATURE
- Multi-modal classification of Alzheimer's disease using nonlinear graph fusion
- (2017) Tong Tong et al. PATTERN RECOGNITION
- Explaining nonlinear classification decisions with deep Taylor decomposition
- (2017) Grégoire Montavon et al. PATTERN RECOGNITION
- Decision forest: Twenty years of research
- (2016) Lior Rokach Information Fusion
- Integrated web visualizations for protein-protein interaction databases
- (2015) Fleur Jeanquartier et al. BMC BIOINFORMATICS
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
- (2015) Sebastian Bach et al. PLoS One
- Knowledge Discovery and interactive Data Mining in Bioinformatics - State-of-the-Art, future challenges and research directions
- (2014) Andreas Holzinger et al. BMC BIOINFORMATICS
- Similarity network fusion for aggregating data types on a genomic scale
- (2014) Bo Wang et al. NATURE METHODS
- Modules, networks and systems medicine for understanding disease and aiding diagnosis
- (2014) Mika Gustafsson et al. Genome Medicine
- The Graph Neural Network Model
- (2008) F. Scarselli et al. IEEE TRANSACTIONS ON NEURAL NETWORKS
Add your recorded webinar
Do you already have a recorded webinar? Grow your audience and get more views by easily listing your recording on Peeref.
Upload NowAsk a Question. Answer a Question.
Quickly pose questions to the entire community. Debate answers and get clarity on the most important issues facing researchers.
Get Started